© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2909
    Prev
    Next
    INDEX
    Explanations

    say residual

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moral
    -24.13
    道德
    -21.50
     Moral
    -20.13
     mor
    -19.25
     morph
    -19.13
    Mor
    -19.13
     pres
    -18.25
    mor
    -17.75
    morph
    -17.63
     PRES
    -17.50
    POSITIVE LOGITS
    余
    54.75
     residual
    42.75
    餘
    42.00
     residue
    37.25
     residuals
    33.00
    残
    31.63
    �
    31.50
     reserve
    31.50
    _residual
    31.38
     residues
    30.38
    Activations Density 0.070%

    No Known Activations